Publications scientifiques

In oncology, the seriousness of the disease amplifies the visibility of radiological errors, leading to both significant individual consequences and broader public health concerns. By leveraging quantitative approaches, the authors reframe the diagnostic process in radiology as a classification problem, a perspective aligned with recent neurocognitive theories on decision-making errors.

This structured model offers a practical framework for conducting root cause analysis of diagnostic errors in radiology and developing effective risk-management strategies.

Cet article passe en revue la variabilité des évaluations en oncologie radiologique, en se concentrant particulièrement sur les critères RECIST 1.1, qui normalisent les évaluations afin d’améliorer la cohérence et la précision. Il explique comment la variabilité découle de facteurs tels que l’expertise du radiologue, la qualité de l’image et la sélection des lésions, et souligne l’importance des protocoles normalisés et de la formation pour atténuer ces problèmes. En s’attaquant aux causes profondes de la variabilité, l’article vise à améliorer la précision des évaluations de la réponse, ce qui se traduit en fin de compte par de meilleurs soins aux patients et de meilleurs résultats cliniques.

Hepatocellular carcinoma (HCC) constitutes a prominent global health challenge. According to the American Association for the Study of Liver Diseases (AASLD) guideline HCC can be diagnosed by imaging examination. However, it shows that contrast-enhanced CT has limited accuracy in the diagnosis of HCC, particularly, small-size HCC lesions (≤ 20 mm) are the most difficult to identify with CT demonstrating sensitivity = 64% [1]. An Artificial Intelligence (AI) algorithm that can analyze liver CT images and localize HCC lesions would be valuable for patients at risk of HCC. Recent studies have presented promising outcomes regarding the application of AI algorithms in HCC diagnosis; However, the efficacy in localizing small-sized HCC lesions in CT images remains uncertain, and there is a need for improvement in reducing the false-positive rate [2-4].